© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18819
    Prev
    Next
    INDEX
    Explanations

    text-generation-webui

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seventy
    0.38
     Mum
    0.38
    Toc
    0.36
    𝙮
    0.36
     Sie
    0.35
     sefer
    0.35
    ﻝ
    0.35
     তো
    0.35
     nose
    0.35
    ítico
    0.34
    POSITIVE LOGITS
     വകു
    0.43
    Ǥ
    0.37
     eigenvectors
    0.36
    റ്റ്
    0.35
     張
    0.35
    していました
    0.35
    kv
    0.34
    ობაში
    0.34
    मिता
    0.34
    직
    0.34
    Activations Density 0.002%

    No Known Activations